Update app.py

app.py

@@ -14,7 +14,7 @@ tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
 # Load the model to CPU first; it will be moved to GPU during processing
 model = AutoModel.from_pretrained(
     model_name,
-    _attn_implementation="flash_attention_2",
+    #_attn_implementation="flash_attention_2",
     trust_remote_code=True,
     use_safetensors=True,
 )